Automated detection of driver fatigue from electroencephalography through wavelet-based connectivity

Ahmadi, Amirmasoud; Bazregarzadeh, Hanieh; Kazemi, Kamran

doi:10.1016/j.bbe.2020.08.009

Cited by 28 publications

(11 citation statements)

References 65 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

Section: Preprocessingmentioning

confidence: 90%

“…Fourth, since one of the objectives of this study is to use minimal EEG signal channels, it is necessary to identify the active electrodes to reduce the computational complexity. In accordance with [24,25,58,59], 12 electrodes, out of the 30 electrodes used for signal recording, were identified in the form of six active regions, on the basis of the electrode weights, for this purpose. Accordingly, only data from the 12 selected channels were used for the compression and data processing, and the rest of the channels were excluded from the processing.…”

Section: Preprocessingmentioning

confidence: 99%

See 1 more Smart Citation

Developing a Deep Neural Network for Driver Fatigue Detection Using EEG Signals Based on Compressed Sensing

et al. 2022

View full text Add to dashboard Cite

In recent years, driver fatigue has become one of the main causes of road accidents. As a result, fatigue detection systems have been developed to warn drivers, and, among the available methods, EEG signal analysis is recognized as the most reliable method for detecting driver fatigue. This study presents an automated system for a two-stage classification of driver fatigue, using a combination of compressed sensing (CS) theory and deep neural networks (DNNs), that is based on EEG signals. First, CS theory is used to compress the recorded EEG data in order to reduce the computational load. Then, the compressed EEG data is fed into the proposed deep convolutional neural network for automatic feature extraction/selection and classification purposes. The proposed network architecture includes seven convolutional layers together with three long short-term memory (LSTM) layers. For compression rates of 40, 50, 60, 70, 80, and 90, the simulation results for a single-channel recording show accuracies of 95, 94.8, 94.6, 94.4, 94.4, and 92%, respectively. Furthermore, by comparing the results to previous methods, the accuracy of the proposed method for the two-stage classification of driver fatigue has been improved and can be used to effectively detect driver fatigue.

show abstract

Section: Preprocessingmentioning

confidence: 90%

Section: Preprocessingmentioning

confidence: 99%

Developing a Deep Neural Network for Driver Fatigue Detection Using EEG Signals Based on Compressed Sensing

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Additionally, some studies did not provide enough details concerning how they perform CV [39,5]. For example, Ahmadi et al [1] aimed to detect driver fatigue by using an expert automatic method based on brain region connectivity. They used an EEG dataset that recorded fatigue and alert states.…”

Section: Cross-validation For Deep Learning Modelmentioning

confidence: 99%

On Time Series Cross-Validation for Deep Learning Classification Model of Mental Workload Levels Based on EEG Signals

Kingphai

Moshfeghi

2023

Lecture Notes in Computer Science

View full text Add to dashboard Cite

The determination of a subject's mental workload (MWL) from an electroencephalogram (EEG) is a well-studied area in the braincomputer interface (BCI) field. A high MWL level can significantly contribute to mental fatigue, decreased performance, and long-term health problems. Inspired by the success of machine learning in various areas, researchers have investigated the use of deep learning models to classify subjects' MWL levels. A common approach that is used to evaluate such classification models is the cross-validation (CV) technique. However, the CV technique used for such models does not take into account the time series nature of EEG signals. Therefore, in this paper we propose a modification of CV techniques, i.e. a blocked form of CV with rolling window and expanding window strategies, which are more suitable for EEG signals. Then, we investigate the effectiveness of the two strategies and also explore the effects of different block sizes for each strategy. We then apply these models to several state-of-the-art deep learning models used for MWL classification from EEG signals using a publicly available dataset, STEW. There were two classification tasks: Task 1-resting vs testing state, and Task 2-low vs moderate vs high MWL. Our results show that the model evaluated by the expanding window strategy, when it was trained using the 90% of data, provided a better performance than the rolling window strategy and that the BGRU-GRU model outperformed the other models for both tasks.

show abstract

“…Wu et al [ 22 ] represented the pilots’ stress detection using a deep learning classifier on the EEG signal. Ahmadi et al [ 23 ] designed a wavelet-based automatic system for mental stress detection in drivers using a Support Vector Machine (SVM) based machine learning classifier. They used eye-tracking technology to record the signals.…”

Section: Introductionmentioning

confidence: 99%

Wearable Flexible Electronics Based Cardiac Electrode for Researcher Mental Stress Detection System Using Machine Learning Models on Single Lead Electrocardiogram Signal

et al. 2022

View full text Add to dashboard Cite

In the modern world, wearable smart devices are continuously used to monitor people’s health. This study aims to develop an automatic mental stress detection system for researchers based on Electrocardiogram (ECG) signals from smart T-shirts using machine learning classifiers. We used 20 subjects, including 10 from mental stress (after twelve hours of continuous work in the laboratory) and 10 from normal (after completing the sleep or without any work). We also applied three scoring techniques: Chalder Fatigue Scale (CFS), Specific Fatigue Scale (SFS), Depression, Anxiety, and Stress Scale (DASS), to confirm the mental stress. The total duration of ECG recording was 1800 min, including 1200 min during mental stress and 600 min during normal. We calculated two types of features, such as demographic and extracted by ECG signal. In addition, we used Decision Tree (DT), Naive Bayes (NB), Random Forest (RF), and Logistic Regression (LR) to classify the intra-subject (mental stress and normal) and inter-subject classification. The DT leave-one-out model has better performance in terms of recall (93.30%), specificity (96.70%), precision (94.40%), accuracy (93.30%), and F1 (93.50%) in the intra-subject classification. Additionally, The classification accuracy of the system in classifying inter-subjects is 94.10% when using a DT classifier. However, our findings suggest that the wearable smart T-shirt based on the DT classifier may be used in big data applications and health monitoring. Mental stress can lead to mitochondrial dysfunction, oxidative stress, blood pressure, cardiovascular disease, and various health problems. Therefore, real-time ECG signals help assess cardiovascular and related risk factors in the initial stage based on machine learning techniques.

show abstract

Automated detection of driver fatigue from electroencephalography through wavelet-based connectivity

Cited by 28 publications

References 65 publications

Developing a Deep Neural Network for Driver Fatigue Detection Using EEG Signals Based on Compressed Sensing

Developing a Deep Neural Network for Driver Fatigue Detection Using EEG Signals Based on Compressed Sensing

On Time Series Cross-Validation for Deep Learning Classification Model of Mental Workload Levels Based on EEG Signals

Wearable Flexible Electronics Based Cardiac Electrode for Researcher Mental Stress Detection System Using Machine Learning Models on Single Lead Electrocardiogram Signal

Contact Info

Product

Resources

About